Triple

T9619493
Position Surface form Disambiguated ID Type / Status
Subject Estha E232304 entity
Predicate familyName P18 FINISHED
Object Ipe
Ipe is an Indian surname commonly associated with Syrian Christian families from the state of Kerala.
E810141 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Ipe | Statement: [Estha, familyName, Ipe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ipe
Context triple: [Estha, familyName, Ipe]
  • A. Guaiúba
    Guaiúba is a municipality in the state of Ceará, Brazil, located in the metropolitan region of Fortaleza.
  • B. Juazeiro
    Juazeiro is a city in the state of Bahia, Brazil, located on the São Francisco River and known for its agricultural production and close integration with the neighboring city of Petrolina.
  • C. Simarouba
    Simarouba is a genus of tropical trees and shrubs known for species like the paradise-tree, some of which are used for timber, traditional medicine, and oil-rich seeds.
  • D. Inga
    Inga are an Indigenous people of the Andean region of Colombia, known for their Quechua-related language and rich traditions in agriculture, herbal medicine, and communal life.
  • E. Inga
    Inga is a comedic, good-natured lab assistant and love interest in Mel Brooks’s film "Young Frankenstein," known for her playful personality and memorable lines.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ipe
Triple: [Estha, familyName, Ipe]
Generated description
Ipe is an Indian surname commonly associated with Syrian Christian families from the state of Kerala.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ipe
Target entity description: Ipe is an Indian surname commonly associated with Syrian Christian families from the state of Kerala.
  • A. Guaiúba
    Guaiúba is a municipality in the state of Ceará, Brazil, located in the metropolitan region of Fortaleza.
  • B. Juazeiro
    Juazeiro is a city in the state of Bahia, Brazil, located on the São Francisco River and known for its agricultural production and close integration with the neighboring city of Petrolina.
  • C. Simarouba
    Simarouba is a genus of tropical trees and shrubs known for species like the paradise-tree, some of which are used for timber, traditional medicine, and oil-rich seeds.
  • D. Inga
    Inga are an Indigenous people of the Andean region of Colombia, known for their Quechua-related language and rich traditions in agriculture, herbal medicine, and communal life.
  • E. Inga
    Inga is a comedic, good-natured lab assistant and love interest in Mel Brooks’s film "Young Frankenstein," known for her playful personality and memorable lines.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca84867bb88190b4b57dd5a56d5691 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9ad295008190a4418d092576cb53 completed April 1, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1796ced5c8190a3f275e03b481a96 completed April 4, 2026, 8:49 p.m.
NEDg Description generation batch_69d17a5df01081909f20c4a722cef83d completed April 4, 2026, 8:53 p.m.
NED2 Entity disambiguation (via description) batch_69d17adb55648190b01060ade60b0fde completed April 4, 2026, 8:55 p.m.
Created at: March 30, 2026, 8:09 p.m.